{"url":"/sota/dialog-relation-extraction-on-dialogre","task":{"name":"Dialog Relation Extraction","url":"/task/dialog-relation-extraction","note":null},"dataset":{"name":"DialogRE","url":"/dataset/dialogre"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Dialog Relation Extraction is the task of predicting the relation type between entities mentioned in dialogue. It uses multiple tokens to capture possible relations between pairs of entities in the dialogue. The popular benchmark for this task is the DialogRE dataset. The models are typically evaluated with the metric of F1 Score for both standard-setting and conversational settings.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1 (v2)","F1c (v2)","F1 (v1)","F1c (v1)","F1 (Chinese)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1 (v2)":"higher","F1c (v2)":null,"F1 (v1)":"higher","F1c (v1)":null,"F1 (Chinese)":"higher"}},"counts":{"rows":17,"rows_with_code":16,"rows_with_paper_page":17,"rows_dated":17,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"HiDialog","metrics":{"F1 (v2)":"77.1","F1c (v2)":"68.2"},"uses_additional_data":false,"paper_date":"2023-04-29","paper":"/paper/hierarchical-dialogue-understanding-with-1","paper_url":"https://arxiv.org/abs/2305.00262v1","paper_title":"Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention","code":"https://github.com/shawx825/hidialog","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"GRASP_Large","metrics":{"F1 (v1)":"75.1","F1 (v2)":"75.5","F1c (v1)":"66.7","F1c (v2)":"67.8"},"uses_additional_data":false,"paper_date":"2022-08-26","paper":"/paper/grasp-guiding-model-with-relational-semantics","paper_url":"https://arxiv.org/abs/2208.12494v4","paper_title":"GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction","code":"https://github.com/rgop13/GRASP","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"DiaRE-D2G","metrics":{"F1 (v2)":"74.5","F1c (v2)":"69.8"},"uses_additional_data":false,"paper_date":"2022-07-30","paper":"/paper/global-inference-with-explicit-syntactic-and","paper_url":"https://www.ijcai.org/proceedings/2022/0570","paper_title":"Global inference with explicit syntactic and discourse structures for dialogue-level relation extraction","code":"https://github.com/scofield7419/DiaRE-D2G","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"TUCORE-GCN_RoBERTa","metrics":{"F1 (v2)":"73.1","F1c (v2)":"65.9"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/graph-based-network-with-contextualized","paper_url":"https://arxiv.org/abs/2109.04008v1","paper_title":"Graph Based Network with Contextualized Representations of Turns in Dialogue","code":"https://github.com/blacknoodle/tucore-gcn","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"SocAoG","metrics":{"F1 (v2)":"69.1","F1c (v2)":"66.5"},"uses_additional_data":false,"paper_date":"2021-06-02","paper":"/paper/socaog-incremental-graph-parsing-for-social","paper_url":"https://arxiv.org/abs/2106.01006v3","paper_title":"SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"GRASP_Base","metrics":{"F1 (v1)":"69.2","F1 (v2)":"69.0","F1c (v1)":"62.4","F1c (v2)":"61.7"},"uses_additional_data":false,"paper_date":"2022-08-26","paper":"/paper/grasp-guiding-model-with-relational-semantics","paper_url":"https://arxiv.org/abs/2208.12494v4","paper_title":"GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction","code":"https://github.com/rgop13/GRASP","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"D-REX_RoBERTa","metrics":{"F1 (v2)":"67.2"},"uses_additional_data":false,"paper_date":"2021-09-10","paper":"/paper/d-rex-dialogue-relation-extraction-with","paper_url":"https://arxiv.org/abs/2109.05126v2","paper_title":"D-REX: Dialogue Relation Extraction with Explanations","code":"https://github.com/alon-albalak/D-REX","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"Dual","metrics":{"F1 (v1)":"67.3","F1 (v2)":"67.1","F1c (v1)":"61.4","F1c (v2)":"61.1"},"uses_additional_data":false,"paper_date":"2021-05-21","paper":"/paper/semantic-representation-for-dialogue-modeling","paper_url":"https://arxiv.org/abs/2105.10188v2","paper_title":"Semantic Representation for Dialogue Modeling","code":"https://github.com/muyeby/AMR-Dialogue","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"SimpleRE","metrics":{"F1 (Chinese)":"65.2","F1 (v1)":"66.3","F1 (v2)":"66.7","F1c (v2)":"63.3"},"uses_additional_data":false,"paper_date":"2020-12-27","paper":"/paper/an-embarrassingly-simple-model-for-dialogue","paper_url":"https://arxiv.org/abs/2012.13873v2","paper_title":"An Embarrassingly Simple Model for Dialogue Relation Extraction","code":"https://github.com/XueFuzhao/SimpleRE","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"TUCORE-GCN_BERT","metrics":{"F1 (v2)":"65.5","F1c (v2)":"60.2"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/graph-based-network-with-contextualized","paper_url":"https://arxiv.org/abs/2109.04008v1","paper_title":"Graph Based Network with Contextualized Representations of Turns in Dialogue","code":"https://github.com/blacknoodle/tucore-gcn","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"Joint_RoBERTa","metrics":{"F1 (v2)":"65.2"},"uses_additional_data":false,"paper_date":"2021-09-10","paper":"/paper/d-rex-dialogue-relation-extraction-with","paper_url":"https://arxiv.org/abs/2109.05126v2","paper_title":"D-REX: Dialogue Relation Extraction with Explanations","code":"https://github.com/alon-albalak/D-REX","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"KnowPrompt","metrics":{"F1 (v1)":"66.0"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/adaprompt-adaptive-prompt-based-finetuning","paper_url":"https://arxiv.org/abs/2104.07650v7","paper_title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","code":"https://github.com/zjunlp/KnowPrompt","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"GDPNet","metrics":{"F1 (v1)":"64.9","F1c (v1)":"60.1"},"uses_additional_data":false,"paper_date":"2020-12-12","paper":"/paper/gdpnet-refining-latent-multi-view-graph-for","paper_url":"https://arxiv.org/abs/2012.06780v1","paper_title":"GDPNet: Refining Latent Multi-View Graph for Relation Extraction","code":"https://github.com/XueFuzhao/GDPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"BERT+SIEF","metrics":{"F1 (v1)":"61.8","F1c (v1)":"58.4"},"uses_additional_data":false,"paper_date":"2022-04-27","paper":"/paper/document-level-relation-extraction-with-3","paper_url":"https://arxiv.org/abs/2204.12679v1","paper_title":"Document-Level Relation Extraction with Sentences Importance Estimation and Focusing","code":"https://github.com/xwjim/sief","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"BERTS","metrics":{"F1 (v1)":"61.2","F1c (v1)":"55.4"},"uses_additional_data":false,"paper_date":"2020-04-17","paper":"/paper/dialogue-based-relation-extraction","paper_url":"https://arxiv.org/abs/2004.08056v1","paper_title":"Dialogue-Based Relation Extraction","code":"https://github.com/nlpdata/dialogre","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":5}},{"rank_in_archive_order":16,"model":"DHGAT","metrics":{"F1 (v1)":"56.1","F1c (v1)":"50.7"},"uses_additional_data":false,"paper_date":"2020-09-10","paper":"/paper/dialogue-relation-extraction-with-document","paper_url":"https://arxiv.org/abs/2009.05092v3","paper_title":"Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks","code":"https://github.com/declare-lab/dialog-HGAT","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"BiLSTM","metrics":{"F1 (v1)":"48.6","F1c (v1)":"45"},"uses_additional_data":false,"paper_date":"2020-04-17","paper":"/paper/dialogue-based-relation-extraction","paper_url":"https://arxiv.org/abs/2004.08056v1","paper_title":"Dialogue-Based Relation Extraction","code":"https://github.com/nlpdata/dialogre","n_code_links":3,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":5}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":20,"n_unverified":11,"n_samples":31,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":39,"n_unverified":18,"n_samples":57,"n_pointer_only_licence":10,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}